diplomat33
Average guy who loves autonomous vehicles
You do realize my first quote where I say Smart Summon is L4 was tongue and cheek right? Did you not see the little emoticons?
You can install our site as a web app on your iOS device by utilizing the Add to Home Screen feature in Safari. Please see this thread for more details on this.
Note: This feature may not be available in some browsers.
Good god, I’d be laughing as hard as Mike is if I hadn’t actually paid $3k for this two years ago. It sounds like they should rename “advanced summon” to “Flintstones mode” with that list of limitations, because pushing the f-ing car seems like it’ll be more efficient than this.
I asked @strangecosmos in another thread to run the numbers on the cost of collecting, storing, retrieving, labeling, and training on this supposedly vast amount of fleet data, but he never responded.
Training machine learning algorithms on large amounts of data is very expensive. If there is any human labeling that is also very expensive,
Amir himself said Tesla hadn't even started working on a simulator
Evidence of state/action data collection X
Evidence of HD Map X
he ignores MobilEye EyeQ4 is actually already ahead with a similar advantage on abstracted data.
Then in my other point i talked about how your own post disproves the statement you made. You said it yourself, Tesla needs HW3 because only that is said to have traffic lights, traffic sign, road signs, road markings, potholes, debris, general object and more accurate detection, etc. Therefore how can they already have the training data they need as you just said? As the current firmware in AP2.X has none of those detection capability?
They do, every one in a while.
State-action pairs for imitation learning don't need to be labelled. The action is the label for the state. In other words, the action is the output that the neural network learns to map to the input, which is the state. This is just good ol' fashioned deep supervised learning. AlphaStar was trained with state-action pairs from StarCraft games that didn't require hand labelling by annotators.
So... Tesla hadn't even started working on a simulator? Not what Amir wrote. An infant isn’t a gamete.
To avoid making this mistake, you can look up the source and quote it rather than going off memory. This might be slightly more inconvenient in the moment, but it can save you time in the long run and give your arguments more credibility. When someone can disprove what you said just by quoting the thing you referenced — multiple times — that makes it hard to trust your claims in the future.
Why do you say there is no evidence Tesla is using imitation learning?
Amir reported in the same article that Tesla is creating HD maps. As I understand it, he even said that Navigate on Autopilot uses HD maps:
"Detailed road maps, on the other hand, are in an even earlier stage at Tesla. These are different from surface-level navigation maps from Google that Tesla owners can use in their vehicle. Autopilot software stepped up reliance on maps for the just-launched feature to help the vehicle merge from one highway to another, in which it is useful to know when you are about to approach such a merge. (It is not clear how well the merge feature works overall.)
The more detailed maps Tesla is building rely on image data that’s collected by Tesla vehicles on the road, in combination with GPS. In the future, these maps might be used to spot construction zones or other hazards and communicate them to other Tesla vehicles so that the Autopilot driving system can avoid them automatically."
In January, I asked Amnon Shashua (the CEO) if Mobileye is using imitation learning and this was his reply:
"Imitation learning is great when you have someone to imitate (like in pattern recognition & NLP). We instead created two layers – one based on “self-play” RL that learns to handle adversarial driving (including non-human) and another layer called RSS which is rule-based."
If you have any evidence Mobileye is collecting state-action pairs for imitation learning from production cars with EyeQ4, please share it.
There are some 80 engineering test cars around the globe, gathering data on the roads and learning about driving in different locations. With so many sensors gathering data, it comes in at "a couple of terabytes per hour per car". But it's data that's essential for developing an autonomous driving policy and it's data that informs the algorithm that will ultimately see the car making decisions.
So if you spot test cars out on the road they aren't necessarily driving autonomously waiting for human intervention, instead they are capturing the human driver's data to learn from the decisions that are being made.
This is interesting. Have you noticed any patterns in when Tesla uploads steering+pedal data, or what other data it uploads alongside it?
I think someone else said that supervised learning won't work because the car doesn't know what your intent is, so it has nothing to compare against. For example, you may be navigating to the airport, but the car has no idea what you are doing. To it, you are randomly changing lanes, etc.
On the other hand, MobilEye’s REM mapping is doing 2) basically. I won’t be digging for their talks on gathering driving interactions in an absracted form and feeding those into NNs for driving policy simulation (which then you can compare your driving to) but that’s something you can do when you are at point 2). Tesla is not.
They are using IL to bootstrap RL 100%.
There are some 80 engineering test cars around the globe, gathering data on the roads and learning about driving in different locations. With so many sensors gathering data, it comes in at "a couple of terabytes per hour per car". But it's data that's essential for developing an autonomous driving policy and it's data that informs the algorithm that will ultimately see the car making decisions.
So if you spot test cars out on the road they aren't necessarily driving autonomously waiting for human intervention, instead they are capturing the human driver's data to learn from the decisions that are being made.
For this assumption to work, you need one of two things:
1) Raw data of the state (ie full-res video from all the cameras)
or
2) Reliable abstraction (ie 3D view of the world)
There is no proof that Tesla is gathering 1) on any significant-enough scale to teach NNs nor is anywhere near reliable enough in their vision engine for 2).
I would equate infancy to haven't started. Haven't started = serious development haven't begun.
So yes, according to Amir, they haven't even started. Simulators built for lane keeping/acc features doesn't count. I already outlined that in my post.
The maps that are downloaded as a preq to use NOA are not HD maps.
they get it with practically every snapshot. About 2 minutes worth of it, I'd estimate.This is interesting. Have you noticed any patterns in when Tesla uploads steering+pedal data, or what other data it uploads alongside it?
they get it with practically every snapshot. About 2 minutes worth of it, I'd estimate.
snapshot requests vary as is the data requested, but typically after a trigger happened a canbus dump (that includes raw radar, but also steering and other such driver input) is sent as a follow on thing 30 seconds later (since it goes back like 2 minutes it's ok)
Tesla has posted public job listings for an “Autopilot Simulation Engineer” and a “Software Engineer, Autopilot Simulation”.
all of that could be requestedThanks! Any camera data? Video or still images?
If the neural network’s mid-level representation (i.e. what’s represented in your videos by bounding boxes, “green carpet”, etc.) were uploaded with snapshots, would you be able to tell?